Mandy Xie

Ph.D. student in Computer Science, Georgia Institute of Technology


I am now a third year Ph.D. student in computer science, working with professor Frank Dellaert at Georgia Institute of Technology. Prior to enrolling in computer science, I completed my master's program in Aerospace Engineering at Georgia Tech, and received my bachelor degree in Mechanical Engineering from Huazhong University of Science and Technology, Wuhan, China.

My current research interests cover various topics in robotics, including but not limited to manipulator dynamics, kinodynamic motion planning and motion generation. I am interested in solving various robotics problems using factor graphs, and learning motion policies from demonstration.

Research Projects

Solve Manipulator Dynamics Problems using Factor Graphs

Manipulator dynamics is one of the most fundamental problems in robotics, and it is considered to be a well studied problem. Various different algorithms have been developed to solve each type of dynamics problems, including inverse, forward and hybrid dynamics problems. However, they are not easily explained in a unified and intuitive way. In this project, our goal is to develop a unified method which solves all types of dynamics problems for robotic manipulators with either open kinematic chains or closed kinematic loops based on factor graphs.

Paper submission:

[1] M. Xie and F. Dellaert. A unified method for solving inverse, forward, and hybrid manipulator dynamics using factor graphs. [PDF]

Solve Kinodynamic Motion Planning Problems using Factor Graphs.

In this project, we proposed a kinodynamic motion planner that is able to produce energy efficient motions by taking the full robot dynamics into account, and making use of gravity, inertia, and momentum to reduce the effort. Given a specific goal state for the robot, we use factor graph to solve a optimal trajectory, which meets not only the requirements of collision avoidance, but also all kinematic and dynamic constraints, such as velocity, acceleration and torque limits. By exploiting the sparsity in factor graphs, we can solve a kinodynamic motion planning problem efficiently, on par with existing optical control methods, and use incremental elimination techniques to achieve an order of magnitude faster replanning

Paper submission:

[1] M. Xie and F. Dellaert. Batch and Incremental Kinodynamic Motion Planning using Dynamic Factor Graphs. [PDF]

Modeling and Simulation for Soft Robotic Arms using Finite Element Method based on Factor Graphs

Soft robots have contunuum solid bodies that is capable of deforming in an infinite number of ways, however, such property presents a formidable challenge to modeling and analysis. Many attempts have been made to establish a general modeling method for soft robots, and finite element method is one of the most popular methods, which has been widely used for both rigid and soft robots. The FEM model can capture all the deformation information, and can represent the robot dynamics accurately. However, using such models is very difficult in a real-time system of control due to the heavy computation involved in solving FEM models. In this project, we are interested in developing FEM models with factor graphs, and taking advantages of the intuitive representation and efficient computation of factor graphs in solving either linear or nonlinear systems.